Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition

Hai Zhao; Chunyu Kit

Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition

Department of Linguistics and Translation

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

104 Citations (Scopus)

Abstract

This paper describes a novel character tagging approach to Chinese word segmentation and named entity recognition (NER) for our participation in Bakeoff-4.¹ It integrates unsupervised segmentation and conditional random fields (CRFs) learning successfully, using similar character tags and feature templates for both word segmentation and NER. It ranks at the top in all closed tests of word segmentation and gives promising results for all closed and open NER tasks in the Bakeoff. Tag set selection and unsupervised segmentation play a critical role in this success. © IJCNLP 2008. All rights reserved.

Original language	English
Title of host publication	IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop
Publisher	Association for Computational Linguistics
Pages	106-111
Publication status	Published - 11 Jan 2008
Event	6th SIGHAN Workshop on Chinese Language Processing (SIGHAN 2008) - Hyderabad, India Duration: 11 Jan 2008 → 12 Jan 2008 https://aclanthology.org/volumes/I08-4/

Publication series

Name	SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP

Conference

Conference	6th SIGHAN Workshop on Chinese Language Processing (SIGHAN 2008)
Abbreviated title	SIGHAN-6
Country/Territory	India
City	Hyderabad
Period	11/01/08 → 12/01/08
Internet address	https://aclanthology.org/volumes/I08-4/

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zhao, H., & Kit, C. (2008). Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition. In IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop (pp. 106-111). (SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP). Association for Computational Linguistics.

Zhao, Hai ; Kit, Chunyu. / Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition. IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop. Association for Computational Linguistics, 2008. pp. 106-111 (SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP).

@inproceedings{626dbc681e5542acb04fb76747d213aa,

title = "Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition",

abstract = "This paper describes a novel character tagging approach to Chinese word segmentation and named entity recognition (NER) for our participation in Bakeoff-4.1 It integrates unsupervised segmentation and conditional random fields (CRFs) learning successfully, using similar character tags and feature templates for both word segmentation and NER. It ranks at the top in all closed tests of word segmentation and gives promising results for all closed and open NER tasks in the Bakeoff. Tag set selection and unsupervised segmentation play a critical role in this success. {\textcopyright} IJCNLP 2008. All rights reserved.",

author = "Hai Zhao and Chunyu Kit",

year = "2008",

month = jan,

day = "11",

language = "English",

series = "SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP",

publisher = "Association for Computational Linguistics",

pages = "106--111",

booktitle = "IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop",

address = "United States",

note = "6th SIGHAN Workshop on Chinese Language Processing (SIGHAN 2008), SIGHAN-6 ; Conference date: 11-01-2008 Through 12-01-2008",

url = "https://aclanthology.org/volumes/I08-4/",

}

Zhao, H & Kit, C 2008, Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition. in IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop. SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP, Association for Computational Linguistics, pp. 106-111, 6th SIGHAN Workshop on Chinese Language Processing (SIGHAN 2008), Hyderabad, India, 11/01/08.

Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition. / Zhao, Hai; Kit, Chunyu.
IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop. Association for Computational Linguistics, 2008. p. 106-111 (SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition

AU - Zhao, Hai

AU - Kit, Chunyu

PY - 2008/1/11

Y1 - 2008/1/11

N2 - This paper describes a novel character tagging approach to Chinese word segmentation and named entity recognition (NER) for our participation in Bakeoff-4.1 It integrates unsupervised segmentation and conditional random fields (CRFs) learning successfully, using similar character tags and feature templates for both word segmentation and NER. It ranks at the top in all closed tests of word segmentation and gives promising results for all closed and open NER tasks in the Bakeoff. Tag set selection and unsupervised segmentation play a critical role in this success. © IJCNLP 2008. All rights reserved.

AB - This paper describes a novel character tagging approach to Chinese word segmentation and named entity recognition (NER) for our participation in Bakeoff-4.1 It integrates unsupervised segmentation and conditional random fields (CRFs) learning successfully, using similar character tags and feature templates for both word segmentation and NER. It ranks at the top in all closed tests of word segmentation and gives promising results for all closed and open NER tasks in the Bakeoff. Tag set selection and unsupervised segmentation play a critical role in this success. © IJCNLP 2008. All rights reserved.

UR - http://www.scopus.com/inward/record.url?scp=84871054273&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84871054273&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP

SP - 106

EP - 111

BT - IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop

PB - Association for Computational Linguistics

T2 - 6th SIGHAN Workshop on Chinese Language Processing (SIGHAN 2008)

Y2 - 11 January 2008 through 12 January 2008

ER -

Zhao H, Kit C. Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition. In IJCNLP 2008 - Sixth SIGHAN Workshop on Chinese Language Processing - Proceedings of the Workshop. Association for Computational Linguistics. 2008. p. 106-111. (SIGHAN - SIGHAN Workshop on Chinese Language Processing, co-located with International Joint Conference on Natural Language Processing, IJCNLP).

Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition

Abstract

Publication series

Conference

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this